Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/msolecki/founder-os/profitability-analysisnpx skills add msolecki/founder-os --skill profitability-analysisgit clone --depth 1 https://github.com/msolecki/founder-osWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/msolecki/founder-os/profitability-analysis)<a href="https://agentmods.dev/skills/msolecki/founder-os/profitability-analysis"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/profitability-analysis.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.01805 |
| Opus 5 | $0.00017 | $0.00903 |
| Sonnet 5 | $0.00007 | $0.00361 |
| Haiku 4.5 | $0.00003 | $0.00180 |
Grade A, and why
profitability-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Profitability Analysis
Aggregate profitability is a lie of averages, and it exists to be reassuring. This skill breaks it apart per client, and the finding is reliably unwelcome: the client the founder likes most is usually the worst-paying one. Rank by effective rate, not by how the calls feel.
When to use
Quarterly. Before every renewal. Before agreeing to more of the same kind of work — "we should do more of these" is a claim about margin, and it is almost always made from a memory of the mood rather than the timesheet.
Inputs
Read first, in order — house rule 1:
metrics.md— collected revenue per client, the target rateclients/— every hour logged per engagement, including the absorbed scopescope-guardcounted and the unbilled hoursdelivery-retrorecoveredoffer.md— what this work was supposed to be priced atingestion-gate— the ranking is arithmetic and needs no gate, but its denominator is not. An hour logged as it happened is first-hand; an hour the founder reconstructs at quarter end is a recollection, and the gate's own rule is that derived claims inherit their weakest input. An effective rate computed from remembered hours is a remembered rate however many decimals it has.
Beliefs
- Margin dies between the work, not in the work. The delivery hours land roughly where they were estimated. It is the waiting, the re-briefing, the chasing and the fourth re-reading of a thread that empty the rate — none of which appear in the deliverable, and all of which belong in the denominator.
- An underpriced client is not a client, it is a template. The founder quotes the next similar project from what they charged this one, so a bad rate propagates to every engagement that resembles it. This quarter's margin is the small part of the cost.
- Revenue per client is a vanity ranking, and the founder's memory uses it instead of this one. The biggest logo is usually mid-table on rate and gets defended anyway, because losing it would be visible to everyone the founder knows. Losing margin is visible to nobody — which is precisely why margin is what gets lost.
- Efficiency is the wrong lever and it is the first one founders reach for. A client at 55% of target is not fixed by faster work: the same client served twice as fast still costs more to serve than they pay, and the founder now has less time in which to notice.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 140 lines · 34 tokens per session scan A 320148c40898
profitability-analysis is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 1,805 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
sector-rotation
行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.